Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words from other languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    л
    0.63
    ל
    0.60
    ват
    0.54
    ل
    0.52
    جور
    0.49
    <sup>
    0.48
    hal
    0.48
     Astros
    0.48
    l
    0.47
     невероят
    0.47
    POSITIVE LOGITS
     bezieht
    0.54
     exudes
    0.49
     relates
    0.48
     enveloping
    0.46
     Kec
    0.46
    esia
    0.45
    ologie
    0.45
    essa
    0.45
    esModule
    0.44
    เข้าไป
    0.44
    Act Density 0.007%

    No Known Activations